Compare/Nova 2.0 Pro Preview (Non-reasoning) vs GPT-4o (Aug '24)

Nova 2.0 Pro Preview (Non-reasoning)vsGPT-4o (Aug '24)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Amazon

Nova 2.0 Pro Preview (Non-reasoning)

Input
$1.25/M
Output
$10/M
Speed
163 tok/s
TTFT
0.48s
OpenAI

GPT-4o (Aug '24)

Input
$2.5/M
Output
$10/M
Speed
84 tok/s
TTFT
0.68s

Winner by Category

Cheaper
Nova 2.0 Pro Preview (Non-reasoning)
Faster (tok/s)
Nova 2.0 Pro Preview (Non-reasoning)
Lower Latency
Nova 2.0 Pro Preview (Non-reasoning)
Benchmarks (10-2)
Nova 2.0 Pro Preview (Non-reasoning)

Pricing Comparison

MetricNova 2.0 Pro Preview (Non-reasoning)GPT-4o (Aug '24)
Input ($/M tokens)$1.25$2.5
Output ($/M tokens)$10$10
Cost for 1M input + 100K output tokens:
Nova 2.0 Pro Preview (Non-reasoning)$2.25
GPT-4o (Aug '24)$3.50

Speed Comparison

Output Speed (tokens/s) — higher is better
Nova 2.0 Pro Preview (Non-reasoning)
163 tok/s
GPT-4o (Aug '24)
84 tok/s
Time to First Token (seconds) — lower is better
Nova 2.0 Pro Preview (Non-reasoning)
0.48s
GPT-4o (Aug '24)
0.68s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
23.118.6
Coding Index
20.516.6
Math Index
30.7
GPQA Diamond
63.6%52.1%
MMLU-Pro
77.2%
LiveCodeBench
47.3%31.7%
AIME 2025
30.7%
MATH-500
79.5%
Humanity's Last Exam
4.0%2.9%
SciCode
28.1%33.1%
IFBench
52.0%36.0%
TerminalBench
16.7%8.3%
Nova 2.0 Pro Preview (Non-reasoning)10 wins
2 winsGPT-4o (Aug '24)

Frequently Asked Questions

Which is cheaper, Nova 2.0 Pro Preview (Non-reasoning) or GPT-4o (Aug '24)?

Nova 2.0 Pro Preview (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.38/M for GPT-4o (Aug '24).

Which model performs better on benchmarks?

Nova 2.0 Pro Preview (Non-reasoning) wins 10 out of 12 benchmarks compared to 2 for GPT-4o (Aug '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Nova 2.0 Pro Preview (Non-reasoning) generates tokens faster at 163 tok/s vs 84 tok/s. Nova 2.0 Pro Preview (Non-reasoning) also has lower time-to-first-token (0.48s vs 0.68s).

When should I use Nova 2.0 Pro Preview (Non-reasoning) vs GPT-4o (Aug '24)?

Choose based on your priorities: Nova 2.0 Pro Preview (Non-reasoning) for lower cost, Nova 2.0 Pro Preview (Non-reasoning) for stronger benchmark performance, and Nova 2.0 Pro Preview (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.